| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01905366783105748, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 6.9997, | |
| "eval_samples_per_second": 94.719, | |
| "eval_steps_per_second": 47.431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "grad_norm": 2.719556141528301e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "grad_norm": 2.3012857127469033e-05, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0050809780882819944, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.2166, | |
| "eval_samples_per_second": 91.872, | |
| "eval_steps_per_second": 46.005, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "grad_norm": 3.317999289720319e-05, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007621467132422992, | |
| "grad_norm": 2.1859506887267344e-05, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00952683391552874, | |
| "grad_norm": 3.495635974104516e-05, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010161956176563989, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.2877, | |
| "eval_samples_per_second": 90.975, | |
| "eval_steps_per_second": 45.556, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011432200698634487, | |
| "grad_norm": 5.0297352572670206e-05, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013337567481740234, | |
| "grad_norm": 4.19372008764185e-05, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015242934264845983, | |
| "grad_norm": 3.232848030165769e-05, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015242934264845983, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.0877, | |
| "eval_samples_per_second": 93.542, | |
| "eval_steps_per_second": 46.842, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01714830104795173, | |
| "grad_norm": 4.935485776513815e-05, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01905366783105748, | |
| "grad_norm": 2.9111788535374217e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1196882657280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |